OVERVIEW

The analysis of the historical series has progressively acquired greater importance in the financial sector. The ability to model, estimate and predict the behavior of time series and its main properties is a fundamental element for those who want to approach the financial field.

AIMS AND CONTENT

LEARNING OUTCOMES

The course introduces a student to modern techniques in the area of financial econometrics; in particular, the interaction between theory and empirical analysis is emphasized.. Students are introduced to time series analysis of linear univariate and multivariate covariance stationary models with short and long memory parameterization. The course then employs linear time series knowledge to introduce students to time series financial econometrics models, particularly discrete-time parametric ARCH models. The main objective of this course is to develop the skills needed for modelling and forecasting assets volatilities and their co-movements in financial markets. The course aims to provide students with a strong theoretical understanding of volatility models and techniques for estimations, assessment and forecasting in financial markets under a variety of degree of shock persistence. Theoretical lectures are complemented by more empirical and applied ones

AIMS AND LEARNING OUTCOMES

The course is designed to introduce the econometric tools used in in time series analysis and finance, and to gain understanding of the sources and characteristic of financial data as well as current and classic applications. The interaction between theory and empirical analysis is emphasised. Students are introduced to time series analysis of linear univariate and multivariate covariance stationary models with short and long memory parameterization. Llinear time series knowledge is employed to introduce students to time series financial econometrics models, particularly discrete- time parametric ARCH models.. The course aims to provide students with a strong theoretical understanding of volatility models and techniques for estimations, assessment and forecasting in financial markets under a variety of degree of shock persistence. 

At the end of the course, students must:

• have acquired the theoretical skills for the analysis of historical series with different levels of persistence and volatility

• be able to implement tools related to model identification and related diagnostics; verify the presence of unit-root, cointegration and its consequences

• have developed a vocabulary and the skills necessary for reading a good part of the literature on financial econometrics

PREREQUISITES

topics related to the basic course of econometrics and statistics, in particular with reference to estimation methods (OLS and Maximum Likelihood) and hypothesis testing, and the fundamentals of matric algebra

TEACHING METHODS

Face-to-face lectures

Groupwork

Exercises (exercises, software etc.)

N.B.

In case of changes in the sanitary and epidemiological situation,.if it is not possible to carry out activities in presence, the methods of delivery of the courses will be adopted decided by the CDD (mixed mode in presence and online), postponing to Aulaweb for any further updates that may occur necessary during the academic year (both as regards the
delivery methods, both as regards the examination procedures), 

SYLLABUS/CONTENT

TOPIC I: LINEAR TIME SERIES ANALYSIS .

• Stochastic processes, covariance stationarity, strict stationarity, unit root processes, fractionally integrated processes, Wold decomposition theorem.
• AR, MA, ARMA,ARIMA,ARFIMA univariate models: estimation and principles of forecasting.
• Unit root tests,long memory tests, cointegration,model diagnostic.

TOPIC II: UNIVARIATE GARCH MODELS.

• Introduction of asset returns
• ARCH model: identification and covariance stationarity conditions ,order identification, estimation, evaluation
• GARCH model: identification and covariance stationarity conditions ,order identification, estimation, evaluation and forecasting.
• Asymmetric GARCH models and leverage effects:EGARCH,QGARCH,GJGARCH,TGARCH: identification and covariance stationarity conditions ,order identification, estimation, evaluation and forecasting.
• Long memory in univariate GARCH models: testing for long memory in the time series domain, forecasting in presence of long memory.

TOPIC  III: VAR MODELS.

• Introduction to VAR models: properties and characteristics
• Econometric approach to VAR and estimation

TOPIC  IV: MULTIVARIATE GARCH MODELS.

• Introduction to Multivariate GARCH MODELS
• Co-movements of financial returns: empirical and theoretical examples. Introduction to MGARCH models and specific issues.
• FACTOR MODELS
• NON PARAMETRIC models
• Testing in MGARCH models

RECOMMENDED READING/BIBLIOGRAPHY

Hamilton "Time series econometrics"

Franq Zaquoian "Garch models"

additional reading will be raccomanded during the course

TEACHERS AND EXAM BOARD

Exam Board

GABRIELE DEANA (President)

ANNA BOTTASSO

SILVIO TRAVERSO

MAURIZIO CONTI (President Substitute)

LESSONS

LESSONS START

September 2021 to  December 2021

Class schedule

FINANCIAL ECONOMETRICS

EXAMS

EXAM DESCRIPTION

Exam is written with open questions, and can be taken in a single test or in two partial tests: in this case the final grade is the average of the marks of the partial tests.

It is also possible to carry out group assignment  that provides bonus points

ASSESSMENT METHODS

The written exam aims to ascertain:
the understanding of the theoretical foundations of the estimated models analyzed
the ability to evaluate the most appropriate estimation model to use according to the research question and available data
the capability to read and interpret the empirical results
Group work aims to evaluate the application of the different contents learned, as well as the ability to work in a group and critical analysis

Exam schedule